Cross-modal Manifold Learning For Cross-modal Retrieval

Abstract

This paper presents a new scalable algorithm for cross-modal similarity preserving retrieval in a learnt manifold space. Unlike existing approaches that compromise between preserving global and local geometries, the proposed technique respects both simultaneously during manifold alignment. The global topologies are maintained by recovering underlying mapping functions in the joint manifold space by deploying partially corresponding instances. The inter-, and intra-modality affinity matrices are then computed to reinforce original data skeleton using perturbed minimum spanning tree (pMST), and maximizing the affinity among similar cross-modal instances, respectively. The performance of proposed algorithm is evaluated upon two multimodal image datasets (coronary atherosclerosis histology and brain MRI) for two applications: classification, and regression. Our exhaustive validations and results demonstrate the superiority of our technique over comparative methods and its feasibility for i

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyconjeti2016cross

Related papers

• Look Before You Leap: Improving Text-based Person Retrieval By Learning A Consistent Cross-modal Common Manifold (2022)15.34
• Adversarial Cross-modal Retrieval Via Learning And Transferring Single-modal Similarities (2019)8.60
• Cross-modal And Multimodal Data Analysis Based On Functional Mapping Of Spectral Descriptors And Manifold Regularization (2021)0.00
• Discriminative Semantic Transitive Consistency For Cross-modal Learning (2021)0.00
• Metric Learning On Manifolds (2019)0.00
• Unsupervised Multi-modal Hashing For Cross-modal Retrieval (2019)8.35
• Mining On Manifolds: Metric Learning Without Labels (2018)14.31
• Maximal Matching Matters: Preventing Representation Collapse For Robust Cross-modal Retrieval (2025)2.26